Human Age Estimation from Gene Expression Data using Artificial Neural\n Networks

2021/11/04 by Salman Mohamadi, Mohamadi, Salman, Gianfranco Doretto +5
Biochemistry, Genetics and Molecular Biology · #Artificial Intelligence (cs.AI) #Epigenetics and DNA Methylation #FOS: Biological sciences #FOS: Computer and information sciences #Genomics (q-bio.GN)

paper · pdf · doi:10.48550/arxiv.2111.02692

openalex publication_date 2021/11/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The study of signatures of aging in terms of genomic biomarkers can be\nuniquely helpful in understanding the mechanisms of aging and developing models\nto accurately predict the age. Prior studies have employed gene expression and\nDNA methylation data aiming at accurate prediction of age. In this line, we\npropose a new framework for human age estimation using information from human\ndermal fibroblast gene expression data. First, we propose a new spatial\nrepresentation as well as a data augmentation approach for gene expression\ndata. Next in order to predict the age, we design an architecture of neural\nnetwork and apply it to this new representation of the original and augmented\ndata, as an ensemble classification approach. Our experimental results suggest\nthe superiority of the proposed framework over state-of-the-art age estimation\nmethods using DNA methylation and gene expression data.\n

Related

• An Information-Theoretic Framework for Identifying Age-Related Genes Using Human Dermal Fibroblast Transcriptome Data
• iTARGET: Interpretable Tailored Age Regression for Grouped Epigenetic Traits
• Partially blind domain adaptation for age prediction from DNA methylation data
• Genome-wide transcriptome profiling and development of age prediction models in the human brain
• U-learning for Prediction Inference via Combinatory Multi-Subsampling: With Applications to LASSO and Neural Networks